Research publications

Ask or Answer: A Decision Framework for Multi-Turn Health Misinformation Intervention ↗

Xiaoying Song, Anirban Saha Anik, Jinyu Liu, Qitao Tan, Geng Yuan, and Lingzi Hong

A decision framework that learns when a health-misinformation intervention should ask for clarification and when it should answer directly.

SciClaimSeekers at CheckThat! 2026: Retrieving Scientific Sources for Social Media Claims with LLM Reranking ↗

Mohotarema Rashid, Nansu Baniya, Anirban Saha Anik, Xiaoying Song and Lingzi Hong

A scientific-source retrieval system that combines initial retrieval with LLM-based reranking for social-media claims.

SourceMinds at CheckThat! 2026: NLI-Grounded Citation Auditing in a Multi-Agent Pipeline for Full Fact-Checking Article Generation ↗

Farhan Sharukh Hasan, Anirban Saha Anik, Eric Liu, Xiaoying Song, Mohotarema Rashid and Lingzi Hong

A multi-agent fact-checking pipeline that audits citation support with natural language inference.

VeriFind at CheckThat! 2026: Enhancing Numerical Claim Verification via Fine-Tuned LLMs

Diana Zhang, Xiaoying Song, Mohotarema Rashid, Anirban Saha Anik, Junhua Ding, and Lingzi Hong

A fine-tuned LLM approach for numerical claim verification that placed second in the shared task.

Multi-Agent Retrieval-Augmented Framework for Evidence-Based Counterspeech Against Health Misinformation →

Anirban Saha Anik, Xiaoying Song, Elliott Wang, Bryan Wang, Bengisu Yarimbas, and Lingzi Hong

Specialized agents retrieve, summarize, generate, and refine evidence-based counterspeech using static and dynamic sources.

Read paper ↗

Speaking at the Right Level: Literacy-Controlled Counterspeech Generation with RAG-RL →

Xiaoying Song, Anirban Saha Anik, Dibakar Barua, Pengcheng Luo, Junhua Ding, and Lingzi Hong

A RAG and reinforcement-learning framework for generating evidence-grounded counterspeech at the reader's health-literacy level.

Read paper ↗

A Dynamic Fusion Model for Consistent Crisis Response ↗

Xiaoying Song, Anirban Saha Anik, Eduardo Blanco, Vanessa Frías-Martínez, and Lingzi Hong

A dynamic fusion framework for consistent, professional, and actionable crisis responses, together with a consistency metric.

ClaimIQ at CheckThat! 2025: Comparing Prompted and Fine-Tuned Language Models for Verifying Numerical Claims ↗

Anirban Saha Anik, Md Fahimul Kabir Chowdhury, Andrew Wyckoff, and Sagnik Ray Choudhury

A comparison of prompted and fine-tuned language models for numerical claim verification.

Dynamic Fusion of Large Language Models for Crisis Communication ↗

Xiaoying Song, Anirban Saha Anik, Vanessa Frías-Martínez, and Lingzi Hong

A fusion approach combining multiple language models and retrieval for timely and actionable crisis communication.

A Hybrid Attention-Guided Fusion Network with Grad-CAM for MPox Skin Lesion Classification ↗

Mithila Arman, Naheyan Prottush, Maher Ali Rusho, Arup Datta, Anirban Saha Anik, Din Mohammad Dohan, Md. Ashiq Ul Islam Sajid, Intezab Alam Sheikh, and Md. Khurshid Jahan

An interpretable attention-guided model for distinguishing MPox from visually similar skin conditions.

Outcome-Based Education: Evaluating Students' Perspectives Using Transformer ↗

Shuvra Smaran Das, Anirban Saha Anik, Md. Kishor Morol, and Mohammad Sakib Mahmood

Transformer-based sentiment analysis and interpretable explanations for evaluating student perspectives on outcome-based education.

A Study on Future Lockdown Predictions Using ANN ↗

Shuvra Smaran Das, Anirban Saha Anik, Md. Muzakker Hossain, Md. Kishor Morol, Fariha Jahan, and Md. Abdullah Al-Jubair

An artificial-neural-network approach to predicting lockdown timing from epidemiological and socioeconomic signals.

A Comparative Analysis for the Detection of COVID-19 from Chest X-ray Dataset ↗

Anirban Saha Anik, Kowshik Chakraborty, Bishowjit Datta, Abdul Kader, and Md. Kishor Morol

A comparative study of EfficientNet variants for COVID-19 detection from chest X-rays.